Maulik Bhatt

PhD student @BerkeleyME | Previously graduated from @iitbombay

[Berkeley AI Research @berkeley_ai]

We could not be prouder of this years BAIR PhD graduates! Follow their journey to see where they go next @baifeng_shi @sea_snell @databoydg @enfleisig @graceluo_ @zhuhl98 @HaozhiQ @jdzamfi @LianJiachen @joshminwookang @junhaobearxiong @kaylolittlejohn @KentKChang @kvablack @KunheYang @lisabdunlap @LongTonyLian @maulik__bhatt @michaelpsenka @nathanlichtle @neerjathakkar @nikita_mehandru @NiklasLauffer @qiyang_li @vbenara05 @vonekels @xiuyu_l @Yiheng_Li_Cal @ZheFu1 Sampada Deglurkar Wei-Jer Chang Yichen Xie Yigit Erginbas

https://t.co/6axNQ64vDg

[Dayi Ethan Dong @dayiethan]

How can agents learn to coordinate without communicating when faced with multiple choices?

In our new work, MIMIC-D, we use decentralized diffusion models to achieve multi-modal, multi-agent coordination!

Paper: https://t.co/Mil1tiJRxu
Website: https://t.co/xLi9OtpKKa

[Negar Mehr @negar_mehr]

Can LLMs revolutionize the way we think about training multi-agent policies?

In our #AAMAS2025 paper, we introduce an LLM-powered critic that enables credit assignment, strong coordination, and explainable MARL! 🧵👇

[Jean-Baptiste Bouvier @JB_Bouvier__]

Very excited to introduce my latest work on generating feasible robot trajectories with diffusion models!

Website: https://t.co/qvIg6RyfmB
Paper: https://t.co/c2QSPxnWZO

Thread ↓

[Maulik Bhatt @maulik__bhatt]

Just yesterday, I reached 100 citations on Google Scholar, and today I passed my PhD qualifying exam, officially becoming a PhD candidate!

I know it ain't much, but it's honest work.

Grateful for every step of the journey!
#PhDCandidate #GradLife

[Maulik Bhatt @maulik__bhatt]

@rohanchandra30 @Drones_MDPI Congratulations, Rohan!

[Maulik Bhatt @maulik__bhatt]

This is a joint work with Yixuan Jia and @negar_mehr. Please check out our findings. Can't wait to connect and learn from fellow robotics researchers at @ieeeiros next week. #Robotics #AI

[Maulik Bhatt @maulik__bhatt]

Excited to present our latest research at #IROS2023! We introduce an efficient game-theoretic planner for constrained interactive trajectory planning, simplifying multi-agent interactions.

Paper:https://t.co/4ee608gggV
Video:https://t.co/3AnP944zCe
Info:https://t.co/9dXIUXrcMy